lucasjinreal / LLaVA-Magvit2Links
LLaVA combines with Magvit Image tokenizer, training MLLM without an Vision Encoder. Unifying image understanding and generation.
☆39Updated last year
Alternatives and similar repositories for LLaVA-Magvit2
Users that are interested in LLaVA-Magvit2 are comparing it to the libraries listed below
Sorting:
- minisora-DiT, a DiT reproduction based on XTuner from the open source community MiniSora☆40Updated last year
- Video dataset dedicated to portrait-mode video recognition.☆55Updated 3 months ago
- imagetokenizer is a python package, helps you encoder visuals and generate visuals token ids from codebook, supports both image and video…☆38Updated last year
- LMM solved catastrophic forgetting, AAAI2025☆45Updated 9 months ago
- AliTok: Towards Sequence Modeling Alignment between Tokenizer and Autoregressive Model☆52Updated 3 months ago
- Inference-only implementation of "One-Step Diffusion Distillation through Score Implicit Matching" [NIPS 2024]☆84Updated last year
- ☆30Updated 2 years ago
- [NeurIPS 2025] HermesFlow: Seamlessly Closing the Gap in Multimodal Understanding and Generation☆73Updated 4 months ago
- The official PyTorch implementation for Improving Long-Text Alignment for Text-to-Image Diffusion Models (LongAlign)☆80Updated 8 months ago
- ☆141Updated last year
- The official implementation of our paper "Cockatiel: Ensembling Synthetic and Human Preferenced Training for Detailed Video Caption"☆38Updated 8 months ago
- ACDiT: Interpolating Autoregressive Conditional Modeling and Diffusion Transformer☆40Updated last year
- Glance: Accelerating Diffusion Models with 1 Sample☆150Updated 3 weeks ago
- Keras implement of Finite Scalar Quantization☆83Updated 2 years ago
- Step3-VL-10B: A compact yet frontier multimodal model achieving SOTA performance at the 10B scale, matching open-source models 10-20x its…☆152Updated this week
- A light-weight and high-efficient training framework for accelerating diffusion tasks.☆51Updated last year
- A big_vision inspired repo that implements a generic Auto-Encoder class capable in representation learning and generative modeling.☆34Updated last year
- ☆31Updated 6 months ago
- ☆141Updated 3 months ago
- [Preprint] GMem: A Modular Approach for Ultra-Efficient Generative Models☆42Updated 10 months ago
- [ICCV 2025] Explore the Limits of Omni-modal Pretraining at Scale☆121Updated last year
- [Arxiv 2024] Official code for MMTrail: A Multimodal Trailer Video Dataset with Language and Music Descriptions☆33Updated 11 months ago
- Explore how to get a VQ-VAE models efficiently!☆66Updated 5 months ago
- UnifiedMLLM: Enabling Unified Representation for Multi-modal Multi-tasks With Large Language Model☆22Updated last year
- A Framework for Decoupling and Assessing the Capabilities of VLMs☆43Updated last year
- The SAIL-VL2 series model developed by the BytedanceDouyinContent Group☆76Updated 4 months ago
- ☆50Updated 7 months ago
- Implementation of the proposed LVMAE, from the paper, Extending Video Masked Autoencoders to 128 frames, in Pytorch☆55Updated last year
- [ECCV'24 Oral] PiTe: Pixel-Temporal Alignment for Large Video-Language Model☆17Updated 11 months ago
- ☆80Updated 3 months ago